Personalized and Context-aware Route Planning for Edge-assisted Vehicles

TL;DR

This paper introduces a personalized route planning framework for autonomous vehicles using graph neural networks and deep reinforcement learning, which tailors routes to individual driver preferences and improves travel efficiency.

Contribution

It presents a novel GNN and DRL-based approach that incorporates driver behavior analysis for personalized route planning, a significant advancement over traditional generic methods.

Findings

Achieves up to 17% improvement in accommodating driver preferences.

Reduces travel time by 33% in the afternoon and 46% in the evening compared to shortest path.

Effectively models road networks and driver preferences using GNN and DRL.

Abstract

Conventional route planning services typically offer the same routes to all drivers, focusing primarily on a few standardized factors such as travel distance or time, overlooking individual driver preferences. With the inception of autonomous vehicles expected in the coming years, where vehicles will rely on routes decided by such planners, there arises a need to incorporate the specific preferences of each driver, ensuring personalized navigation experiences. In this work, we propose a novel approach based on graph neural networks (GNNs) and deep reinforcement learning (DRL), aimed at customizing routes to suit individual preferences. By analyzing the historical trajectories of individual drivers, we classify their driving behavior and associate it with relevant road attributes as indicators of driver preferences. The GNN is capable of representing the road network as graph-structured data effectively, while DRL is capable of making decisions utilizing reward mechanisms to optimize route selection with factors such as travel costs, congestion level, and driver satisfaction. We evaluate our proposed GNN-based DRL framework using a real-world road network and demonstrate its ability to accommodate driver preferences, offering a range of route options tailored to individual drivers. The results indicate that our framework can select routes that accommodate driver's preferences with up to a 17% improvement compared to a generic route planner, and reduce the travel time by 33% (afternoon) and 46% (evening) relatively to the shortest distance-based approach.